© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40310
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Greek
    -0.29
    quake
    -0.29
    Greek
    -0.27
    临è¿ij
    -0.26
    headed
    -0.24
    ields
    -0.23
     Athens
    -0.23
    smooth
    -0.23
     Greece
    -0.23
    çĶļèĩ³è¿ŀ
    -0.23
    POSITIVE LOGITS
    æĺ¯ä¸ŃåĽ½
    0.29
    eta
    0.29
    形象
    0.26
     eta
    0.26
    çī²
    0.25
    æĪIJ为ä¸ŃåĽ½
    0.25
    æĺ¯æľī
    0.24
    è¿Ļ个èģĮä¸ļ
    0.24
     ún
    0.24
     Serge
    0.23
    Activations Density 0.041%

    No Known Activations